spaCy/spacy/lang/bg/__init__.py

32 lines
907 B
Python

from ...attrs import LANG
from ...language import BaseDefaults, Language
from ...util import update_exc
from ..punctuation import (
COMBINING_DIACRITICS_TOKENIZER_INFIXES,
COMBINING_DIACRITICS_TOKENIZER_SUFFIXES,
)
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from .lex_attrs import LEX_ATTRS
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class BulgarianDefaults(BaseDefaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: "bg"
lex_attr_getters.update(LEX_ATTRS)
stop_words = STOP_WORDS
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
suffixes = COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
infixes = COMBINING_DIACRITICS_TOKENIZER_INFIXES
class Bulgarian(Language):
lang = "bg"
Defaults = BulgarianDefaults
__all__ = ["Bulgarian"]